Previous abstract | Contents | Next abstract

Learning attribute values in typed unification grammers

We present Generalised Reduction (GR), a learning technique for generalising attribute/feature values in typed-unification grammars. GR eliminates as many as possible of the feature constraints (FCs) from the type feature structures (FSs) while applying a criterion of preserving the parsing results on a given, training corpus. For parsing with GR-restricted rule FSs, and for checking the correctness of obtained parses on other corpora, one may use a new form FS unification which we call two-step unification to speed up parsing. We report results on a large-scale HPSG grammar for English.


Liviu Ciortuz, Learning attribute values in typed unification grammers. In: Dan Roth and Antal van den Bosch (eds.), Proceedings of CoNLL-2002, Taipei, Taiwan, 2002, pp. 70-76. [ps] [ps.gz] [pdf] [bibtex]
Last update: September 07, 2002. erikt@uia.ua.ac.be